3 papers
cs.CV2026
Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention
Alexandru Crişan, Diana Borza
Tracking residual tumor after surgery is essential for catching recurrence early, but automating post-operative glioma segmentation remains a difficult task. Although transformer-b…
cs.CV2020
An Attention-Based Deep Learning Model for Multiple Pedestrian Attributes Recognition
Ehsan Yaghoubi, Diana Borza, João Neves +2
The automatic characterization of pedestrians in surveillance footage is a tough challenge, particularly when the data is extremely diverse with cluttered backgrounds, and subjects…
cs.LG2020
Person Re-identification: Implicitly Defining the Receptive Fields of Deep Learning Classification Frameworks
Ehsan Yaghoubi, Diana Borza, Aruna Kumar +1
The \emph{receptive fields} of deep learning classification models determine the regions of the input data that have the most significance for providing correct decisions. The prim…